© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 176
    Prev
    Next
    INDEX
    Explanations

    terms related to financial obligations and the qualifications for exclusions from taxable income

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vium
    -0.58
    gonic
    -0.57
    Ārējās
    -0.55
    niająca
    -0.55
    Välislingid
    -0.53
     symboli
    -0.53
     esternos
    -0.52
     Chwiliwch
    -0.52
     doInBackground
    -0.51
    NUMX
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    0.71
     taxable
    0.69
     IRC
    0.65
     disallowed
    0.61
     NOL
    0.60
     deductions
    0.59
     deductible
    0.59
     deduction
    0.58
     qualified
    0.57
    IRC
    0.57
    Activations Density 0.652%

    No Known Activations